Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical measurements and specifications related to dimensions or sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dimensions and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inWeight
    -0.57
     propOrder
    -0.52
     uLocal
    -0.50
    的好
    -0.43
    idt
    -0.42
    悴
    -0.41
    msgTypes
    -0.40
    addGap
    -0.40
    vaders
    -0.40
    CodeAttribute
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.57
    ConstraintMaker
    0.46
     Италијани
    0.42
    uxxxx
    0.42
     cheval
    0.39
     '{@
    0.39
    ✭✭
    0.38
     khổ
    0.38
     ब्रेकडाउन
    0.37
     betweenstory
    0.37
    Act Density 0.060%

    No Known Activations